{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HZUTTGM25COFMI7SWAH4VTFVAE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"291a6262ada173dde73c498e0ca875c835f0a4e058555f2162998751959f33d7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T01:38:42Z","title_canon_sha256":"f1f0ef6fec16a9954e3bef87ab29d12323a7e9b251d48ac1c10f93a815163559"},"schema_version":"1.0","source":{"id":"2411.00299","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00299","created_at":"2026-07-05T09:36:15Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00299v2","created_at":"2026-07-05T09:36:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00299","created_at":"2026-07-05T09:36:15Z"},{"alias_kind":"pith_short_12","alias_value":"HZUTTGM25COF","created_at":"2026-07-05T09:36:15Z"},{"alias_kind":"pith_short_16","alias_value":"HZUTTGM25COFMI7S","created_at":"2026-07-05T09:36:15Z"},{"alias_kind":"pith_short_8","alias_value":"HZUTTGM2","created_at":"2026-07-05T09:36:15Z"}],"graph_snapshots":[{"event_id":"sha256:618c44a3d0247334647cf5311b9ef1070bff1642e07b1677bfbc893b1a4c9c60","target":"graph","created_at":"2026-07-05T09:36:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.00299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating accurate radiology reports from medical images is a clinically important but challenging task. While current Vision Language Models (VLMs) show promise, they are prone to generating hallucinations, potentially compromising patient care. We introduce RadFlag, a black-box method to enhance the accuracy of radiology report generation. Our method uses a sampling-based flagging technique to find hallucinatory generations that should be removed. We first sample multiple reports at varying temperatures and then use a Large Language Model (LLM) to identify claims that are not consistently s","authors_text":"Julian Acosta, L. John Fahrner, Oishi Banerjee, Pranav Rajpurkar, Serena Zhang, Sraavya Sambara","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T01:38:42Z","title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00299","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d22de571809261f225b2d6bb6c5d37db6a2e8384890ed9b47f35d9227abcd2fd","target":"record","created_at":"2026-07-05T09:36:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"291a6262ada173dde73c498e0ca875c835f0a4e058555f2162998751959f33d7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T01:38:42Z","title_canon_sha256":"f1f0ef6fec16a9954e3bef87ab29d12323a7e9b251d48ac1c10f93a815163559"},"schema_version":"1.0","source":{"id":"2411.00299","kind":"arxiv","version":2}},"canonical_sha256":"3e6939999ae89c5623f2b00fcaccb5012c513d8af9d8bbcbbbf6224fb2883dd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e6939999ae89c5623f2b00fcaccb5012c513d8af9d8bbcbbbf6224fb2883dd9","first_computed_at":"2026-07-05T09:36:15.727297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:15.727297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"siiPGkYWAQcWFifY5XMHeqWklcJFlO7AgjOBPh2tfGh6BtROB3jxwB8ssESB6BYzzwOk0WJuP2bkGwRyRca5Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:15.727849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00299","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d22de571809261f225b2d6bb6c5d37db6a2e8384890ed9b47f35d9227abcd2fd","sha256:618c44a3d0247334647cf5311b9ef1070bff1642e07b1677bfbc893b1a4c9c60"],"state_sha256":"6756b50a38ef9c212948aa11533d9040a38c5b3d5213d19af05c2355e26f44c7"}